Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    commas

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     People
    -0.07
     grandes
    -0.07
    付け
    -0.07
    سنة
    -0.07
     Beh
    -0.07
    VE
    -0.07
     former
    -0.07
    INU
    -0.07
     �
    -0.07
    BUS
    -0.07
    POSITIVE LOGITS
     AUTHOR
    0.07
     paylaş
    0.07
     waived
    0.07
     *__
    0.06
     nl
    0.06
     desi
    0.06
    lander
    0.06
    <>("
    0.06
    を選ぶ
    0.06
    lands
    0.06
    Act Density 0.002%

    No Known Activations